A scalable cloud-based framework for multi-modal mapping across single neuron omics, morphology and electrophysiology

一个可扩展的基于云的框架，用于跨单个神经元组学、形态学和电生理学的多模式映射

• 批准号: 10725550
• 负责人: Bing-Xing Huo
• 金额: $ 241.52万
• 依托单位: BROAD INSTITUTE, INC.
• 依托单位国家: 美国
• 财政年份: 2023
• 资助国家: 美国
• 起止时间: 2023-08-21 至 2026-08-20
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10725550
• 关键词: Adopted; Adoption; Agreement; Algorithms; Atlases; Awareness; BRAIN initiative; Brain; Categories; Cells; Classification; Cloud Computing; Collaborations; Communities; Data; Data Analyses; Data Set; Discipline; Documentation; Ecosystem; Electrophysiology (science); FAIR principles; Grouping; Individual; Knowledge; Learning; Maps; Measurement; Metadata; Methodology; Methods; Microscopy; Modality; Modeling; Molecular; Molecular Biology; Morphology; Nervous System; Neurons; Neurosciences; Peer Review; Phenotype; Protocols documentation; Publishing; Research; Resources; Scientist; Source; Subgroup; Training; Visualization; Visualization software; Work; analytical tool; brain cell; cell type; cloud based; community engagement; computational platform; data integration; data portal; data repository; data standards; hackathon; improved; indexing; insight; interactive tool; invention; knowledge integration; machine learning method; multimodal data; multimodality; neurophysiology; novel; open data; open source; outreach; query tools; repository; scale up; supervised learning; tool; transcriptomics; user-friendly; vector

Project Summary Categorizing individual neurons into different groups, or cell types, is a classical approach to studying the nervous system. With increasingly more tools being invented to observe the neurons, new criteria were created to characterize different aspects, or modalities, of the cells. While these modality-specific categorizations have enabled in-depth knowledge in neuroscience, the inconsistencies across different criteria leave data integration across modalities technically difficult. In addition, disagreements of “similar cells” using different categorization criteria have resulted in division of the neuroscience community into modality-centric subgroups. To solve this problem, objective approaches to define cell similarities incorporating multiple modalities must be established and developed in a way that is open, accessible, and engaging to the neuroscience community at large. We propose to develop a broadly accessible cloud-based framework toward an integrative, multi-modal brain cell atlas using novel, scalable analytics tools, leveraging federated BRAIN Initiative resources and community engagement. The self-supervised learning methodology is purely data-driven, and allows highly accurate identification of similar cells based on single or multiple modalities of measurements, without presumption about modality-specific classes. It also enables cross-modality mapping, where unobserved measurements can be inferred from single-modal data, achieving computational “scale-up” of the brain cell mapping efforts in low- throughput modalities such as electrophysiology or morphology. With more multimodal data being collected and added to the study, the algorithm accuracy of this inference will continue to grow in an automated way. The open-source methodology will be productionized into cloud-native pipelines for individual modalities and for cross-modality mapping, and installed in a cloud computing workbench as a part of the ecosystem, for scalable, open data analyses. This cloud ecosystem will demonstrate access to BRAIN Initiative data repositories hosting molecular (NeMO), neurophysiology (DANDI), and microscopy (BIL) data, such that datasets from different sources can be brought into a common workspace for integrative analyses. Furthermore, the cloud ecosystem will provide a user-friendly data portal for visualization and navigation of the multi-modal single cell data from the repositories, as well as exploring the cell similarity query results. This ecosystem will support FAIR principles and promote collaborative research and seek for extended integrations with data repositories. Through broad engagement and outreach to neuroscience communities, this project will provide resources for building an integrated brain cell atlas and facilitate the multimodal characterization of the brain.

项目摘要 将单个神经元分类为不同的组或细胞类型，是研究神经系统的经典方法。 系统随着越来越多的工具被发明来观察神经元，新的标准被创造出来， 表征细胞的不同方面或形态。虽然这些特定模式的分类 在神经科学方面的深入知识，不同标准之间的不一致性使数据集成 在技术上很困难。此外，使用不同分类的“相似细胞”的分歧 标准导致神经科学界分为以模态为中心的亚组。解决这个 问题，必须建立客观的方法来定义包含多种模态的细胞相似性 并以一种开放的、可访问的、吸引神经科学界的方式发展。我们 我建议开发一个广泛访问的基于云的框架，以实现一个综合的、多模式的脑细胞。 使用新颖、可扩展的分析工具，利用联合BRAIN Initiative资源和社区， 订婚自我监督学习方法纯粹是数据驱动的，并且允许高度准确的 基于单个或多个测量模态识别相似细胞，而不假设 特定于模态的类。它还支持跨模态映射，其中可以使用未观察到的测量结果。 从单模态数据推断，在低- 例如电生理学或形态学的通量模态。随着更多的多模态数据被收集， 在这项研究中，这种推理的算法准确性将以自动化的方式继续增长。的 开源方法将被生产化到云原生管道中，用于单个模式和 跨模态映射，并作为生态系统的一部分安装在云计算工作台中，用于可扩展， 开放数据分析。这个云生态系统将展示对BRAIN Initiative数据存储库的访问， 分子（NeMO），神经生理学（DANDI）和显微镜（BIL）数据，使得来自不同的数据集 可以将各种来源纳入一个共同的工作空间，以便进行综合分析。此外，云生态系统 将提供一个用户友好的数据门户，用于可视化和导航来自 存储库，以及探索细胞相似性查询结果。这个生态系统将支持公平原则 促进合作研究，并寻求与数据库的扩展集成。通过广泛 参与和推广神经科学社区，该项目将提供资源，建立一个 整合的脑细胞图谱，并促进大脑的多模态表征。